Late-Onset Sepsis Mortality among Preterm Infants: Beyond Time to First Antibiotics

Objective: To investigate the impact of timing, in vitro activity and appropriateness of empirical antimicrobials on the outcome of late-onset sepsis among preterm very low birth weight infants that are at high risk of developing meningitis. Study design: This retrospective study included 83 LOS episodes in 73 very low birth weight infants born at <= 32 weeks' gestation with positive blood and/or cerebrospinal fluid culture or polymerase chain reaction at >72 h of age. To define the appropriateness of empirical antimicrobials we considered both their in vitro activity and their ideal delivery through the blood-brain barrier when meningitis was confirmed or not ruled out through a lumbar puncture. The primary outcome was sepsis-related mortality. The secondary outcome was the development of brain lesions. Timing, in vitro activity and appropriateness of empirical antimicrobials, were compared between fatal and non-fatal episodes. Uni- and multi-variable analyses were carried out for the primary outcome. Results: Time to antibiotics and in vitro activity of empirical antimicrobials were similar between fatal and non-fatal cases. By contrast, empirical antimicrobials were appropriate in a lower proportion of fatal episodes of late-onset sepsis (4/17, 24%) compared to non-fatal episodes (39/66, 59%). After adjusting for Gram-negative vs. Gram-positive pathogen and for other supportive measures (time to volume administration), inappropriate empirical antimicrobials remained associated with mortality (aOR, 10.3; 95% CI, 1.4-76.8, p = 0.023), while timing to first antibiotics was not (aOR 0.9; 95% CI, 0.7-1.2, p = 0.408; AUC = 0.88). The association between appropriate antimicrobials and brain sequelae was also significant (p = 0.024). Conclusions: The risk of sepsis-related mortality and brain sequelae in preterm very low birth weight infants is significantly associated with the appropriateness (rather than the timing and the in vitro activity) of empirical antimicrobials. Until meningitis is ruled out through lumbar puncture, septic very low birth weight infants at high risk of mortality should receive empiric antimicrobials with high delivery through the blood-brain barrier.